Neural decoding of gait phases during motor imagery and improvement of the decoding accuracy by concurrent action observation

Hikaru Yokoyama, Naotsugu Kaneko, Katsumi Watanabe, Kimitaka Nakazawa*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Objective. Brain decoding of motor imagery (MI) not only is crucial for the control of neuroprosthesis but also provides insights into the underlying neural mechanisms. Walking consists of stance and swing phases, which are associated with different biomechanical and neural control features. However, previous knowledge on decoding the MI of gait is limited to simple information (e.g. the classification of 'walking' and 'rest'). Approach. Here, we investigated the feasibility of electroencephalogram (EEG) decoding of the two gait phases during the MI of walking and whether the combined use of MI and action observation (AO) would improve decoding accuracy. Main results. We demonstrated that the stance and swing phases could be decoded from EEGs during MI or AO alone. We also demonstrated the decoding accuracy during MI was improved by concurrent AO. The decoding models indicated that the improved decoding accuracy following the combined use of MI and AO was facilitated by the additional information resulting from the concurrent cortical activations related to sensorimotor, visual, and action understanding systems associated with MI and AO. Significance. This study is the first to show that decoding the stance versus swing phases during MI is feasible. The current findings provide fundamental knowledge for neuroprosthetic design and gait rehabilitation, and they expand our understanding of the neural activity underlying AO, MI, and AO + MI of walking. Novelty and significance Brain decoding of detailed gait-related information during motor imagery (MI) is important for brain-computer interfaces (BCIs) for gait rehabilitation. This study is the first to show the feasibility of EEG decoding of the stance versus swing phases during MI. We also demonstrated that the combined use of MI and action observation (AO) improves decoding accuracy, which is facilitated by the concurrent and synergistic involvement of the cortical activations for MI and AO. These findings extend the current understanding of neural activity and the combined effects of AO and MI and provide a basis for effective techniques for walking rehabilitation.

Original languageEnglish
Article number046099
JournalJournal of Neural Engineering
Volume18
Issue number4
DOIs
Publication statusPublished - 2021 Aug

Keywords

  • EEG
  • action observation
  • brain decoding
  • walking, motor imagery

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Fingerprint

Dive into the research topics of 'Neural decoding of gait phases during motor imagery and improvement of the decoding accuracy by concurrent action observation'. Together they form a unique fingerprint.

Cite this